Neolithic period to the Industrial Revolution and includes information reviewed and assembled by history experts and graduate research assistants.

Multi-label classification (MLC) often suffers from performance disparities across labels. We propose \textbf{FairPO}, a framework combining preference-based loss and group-robust optimization to improve fairness by targeting underperforming labels. FairPO partitions labels into a \textit{privileged} set for targeted improvement and a \textit{non-privileged} set to maintain baseline performance. For privileged labels, a DPO-inspired preference loss addresses hard examples by correcting ranking errors between true labels and their confusing counterparts. A constrained objective maintains performance for non-privileged labels, while a Group Robust Preference Optimization (GRPO) formulation adaptively balances both objectives to mitigate bias. We also demonstrate FairPO's versatility with reference-free variants using Contrastive (CPO) and Simple (SimPO) Preference Optimization.

In non-truthful auctions such as first-price and all-pay auctions, the independent strategic behaviors of bidders, with the corresponding Bayes-Nash equilibrium notion, are notoriously difficult to characterize and can cause undesirable outcomes. An alternative approach to achieve better outcomes in non-truthful auctions is to coordinate the bidders: let a mediator make incentive-compatible recommendations of correlated bidding strategies to the bidders, namely, implementing a Bayes correlated equilibrium (BCE). The implementation of BCE, however, requires knowledge of the distributions of bidders' private valuations, which is often unavailable. We initiate the study of the sample complexity of learning Bayes correlated equilibria in non-truthful auctions. We prove that the set of strategic-form BCEs in a large class of non-truthful auctions, including first-price and all-pay auctions, can be learned with a polynomial number $\tilde O(\frac{n}{\varepsilon^2})$ of samples of bidders' values. This moderate number of samples demonstrates the statistical feasibility of learning to coordinate bidders. Our technique is a reduction to the problem of estimating bidders' expected utility from samples, combined with an analysis of the pseudo-dimension of the class of all monotone bidding strategies.

Section A provides more details about our algorithms. In particular, Section A.1 describes the Section A.2 describes the REx implementation of invariance in Section A.3 discusses the two implementation of the self-training used in our experiments: Section B gives the preliminaries of group theory. Section C gives the full proof of our theorem. Section E shows more comparisons and standard deviations on WILDS 2.0 benchmark [ The setup instructions and commands used in our experiments are included in the README.md Self-training loss α Self-training loss weight β Invariance loss weight Symbol in Theory G Group of semantics X Feature space H Subgroup of G that transforms environmental feature e g x Group action Table A1: List of abbreviations and symbols used in the paper. 1 A Additional Details on Algorithm REx circumvents the challenging bi-level optimization from line 2 of Eq. (2) by adding the following Please refer to [8] for a theoretical explanation.

Molecular docking is a core tool in drug discovery for predicting ligand-target interactions. Despite the availability of diverse search-based and machine learning approaches, no single docking algorithm consistently dominates, as performance varies by context. To overcome this challenge, algorithm selection frameworks such as GNNAS-Dock, built on graph neural networks, have been proposed. This study introduces an enhanced system, MC-GNNAS-Dock, with three key advances. First, a multi-criteria evaluation integrates binding-pose accuracy (RMSD) with validity checks from PoseBusters, offering a more rigorous assessment. Second, architectural refinements by inclusion of residual connections strengthen predictive robustness. Third, rank-aware loss functions are incorporated to sharpen rank learning. Extensive experiments are performed on a curated dataset containing approximately 3200 protein-ligand complexes from PDBBind. MC-GNNAS-Dock demonstrates consistently superior performance, achieving up to 5.4% (3.4%) gains under composite criteria of RMSD below 1Å (2Å) with PoseBuster-validity compared to the single best solver (SBS) Uni-Mol Docking V2.

Concept Bottleneck Models (CBMs) propose to enhance the trustworthiness of AI systems by constraining their decisions on a set of human-understandable concepts. However, CBMs typically assume that datasets contain accurate concept labels-an assumption often violated in practice, which we show can significantly degrade performance (by 25% in some cases). To address this, we introduce the Concept Preference Optimization (CPO) objective, a new loss function based on Direct Preference Optimization, which effectively mitigates the negative impact of concept mislabeling on CBM performance. We provide an analysis of key properties of the CPO objective, showing it directly optimizes for the concept's posterior distribution, and contrast it against Binary Cross Entropy (BCE), demonstrating that CPO is inherently less sensitive to concept noise. We empirically confirm our analysis by finding that CPO consistently outperforms BCE on three real-world datasets, both with and without added label noise. We make our code available on Github.

As proved by Feng et al. (2021), the binary cross-entropy loss We include more results on teacher model and teacher model + {DRO (Hashimoto et al., 2018) /ARL (Lahoti et al., 2020) / FairRF (Zhao et al., 2022) /our knowledge distillation} in Tab. Effect of our label smoothing can be observed by comparing between "Teacher (with hard label)" and "Teacher (with softmax/linear label)" in the 6 tables. Here the capacity is the same, the only difference is the label smoothing. Here the training method is the same, only difference is capacity. Table 8: Results on COMP AS dataset with sensitive attribute race .